© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10083
    Prev
    Next
    INDEX
    Explanations

    we/Our + possessive/action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¨ĺå¨ĺ
    -0.12
    奴
    -0.11
    è¿ĺæľīä»Ģä¹Ī
    -0.11
    ç¾İ人
    -0.10
    奢
    -0.09
    çĿ¹
    -0.09
    夯å®ŀ
    -0.09
    ETA
    -0.09
    ä¸Ģ头
    -0.09
    è¾Ļ
    -0.09
    POSITIVE LOGITS
    建议
    0.13
     suggestion
    0.10
    建èŃ°
    0.10
     advice
    0.09
    INY
    0.09
    æݨèįIJ
    0.08
    æĥĺ
    0.08
    ä»ĭåħ¥
    0.08
    客æĪ·æıIJä¾Ľ
    0.08
     Dick
    0.08
    Activations Density 0.113%

    No Known Activations